Straight to the Tree: Constituency Parsing with Neural Syntactic Distance
arXiv:1806.04168
Abstract
In this work, we propose a novel constituency parsing scheme. The model predicts a vector of real-valued scalars, named syntactic distances, for each split position in the input sentence. The syntactic distances specify the order in which the split points will be selected, recursively partitioning the input, in a top-down fashion. Compared to traditional shift-reduce parsing schemes, our approach is free from the potential problem of compounding errors, while being faster and easier to parallelize. Our model achieves competitive performance amongst single model, discriminative parsers in the PTB dataset and outperforms previous models in the CTB dataset.
arXiv commentPublished at ACL2018
References in corpus (6)
- Non-Autoregressive Neural Machine Translation
- Regularizing and Optimizing LSTM Language Models
- Structured Training for Neural Network Transition-Based Parsing
- Neural Language Modeling by Jointly Learning Syntax and Lexicon
- Effective Inference for Generative Neural Parsing
- Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles